File size: 17,494 Bytes
3e1d9f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
# copy from fastchat: https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
"""
Conversation prompt templates.
"""

import dataclasses
from enum import auto, Enum
from typing import List, Tuple, Any, Dict


class SeparatorStyle(Enum):
    """Separator styles."""

    ADD_COLON_SINGLE = auto()
    ADD_COLON_TWO = auto()
    ADD_SPACE_TWO = auto()
    NO_COLON_SINGLE = auto()
    BAIZE = auto()
    DOLLY = auto()
    RWKV = auto()
    PHOENIX = auto()
    NEW_LINE = auto()
    BILLA = auto()


@dataclasses.dataclass
class Conversation:
    """A class that keeps all conversation history."""

    # The name of this template
    name: str
    # System prompts
    system: str
    # Two roles
    roles: List[str]
    # All messages
    messages: List[List[str]]
    # Offset of few shot examples
    offset: int
    # Separators
    sep_style: SeparatorStyle
    sep: str
    sep2: str = None
    # Stop criteria (the default one is EOS token)
    stop_str: str = None
    # Stops generation if meeting any token in this list
    stop_token_ids: List[int] = None

    # Used for the state in the gradio servers.
    # TODO(lmzheng): move this out of this class.
    conv_id: Any = None
    skip_next: bool = False
    model_name: str = None

    def get_prompt(self) -> str:
        """Get the prompt for generation."""
        if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
            ret = self.system + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
            seps = [self.sep, self.sep2]
            ret = self.system + seps[0]
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ": " + message + seps[i % 2]
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.ADD_SPACE_TWO:
            seps = [self.sep, self.sep2]
            ret = self.system + seps[0]
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + " " + message + seps[i % 2]
                else:
                    ret += role + ""
            return ret
        elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
            ret = self.system
            for role, message in self.messages:
                if message:
                    ret += role + message + self.sep
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.BAIZE:
            ret = self.system + "\n"
            for role, message in self.messages:
                if message:
                    ret += role + message + "\n"
                else:
                    ret += role
            return ret
        elif self.sep_style == SeparatorStyle.DOLLY:
            seps = [self.sep, self.sep2]
            ret = self.system
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += role + ":\n" + message + seps[i % 2]
                    if i % 2 == 1:
                        ret += "\n\n"
                else:
                    ret += role + ":\n"
            return ret
        elif self.sep_style == SeparatorStyle.RWKV:
            ret = self.system
            for i, (role, message) in enumerate(self.messages):
                if message:
                    ret += (
                            role
                            + ": "
                            + message.replace("\r\n", "\n").replace("\n\n", "\n")
                    )
                    ret += "\n\n"
                else:
                    ret += role + ":"
            return ret
        elif self.sep_style == SeparatorStyle.PHOENIX:
            ret = self.system
            for role, message in self.messages:
                if message:
                    ret += role + ": " + "<s>" + message + "</s>"
                else:
                    ret += role + ": " + "<s>"
            return ret
        elif self.sep_style == SeparatorStyle.NEW_LINE:
            ret = self.system + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + "\n" + message + self.sep
                else:
                    ret += role + "\n"
            return ret
        elif self.sep_style == SeparatorStyle.BILLA:
            ret = self.system + self.sep
            for role, message in self.messages:
                if message:
                    ret += role + ": " + message + self.sep
                else:
                    ret += role + ": "  # must be end with a space
            return ret
        else:
            raise ValueError(f"Invalid style: {self.sep_style}")

    def append_message(self, role: str, message: str):
        """Append a new message."""
        self.messages.append([role, message])

    def to_gradio_chatbot(self):
        """Convert the history to gradio chatbot format"""
        ret = []
        for i, (role, msg) in enumerate(self.messages[self.offset:]):
            if i % 2 == 0:
                ret.append([msg, None])
            else:
                ret[-1][-1] = msg
        return ret

    def to_openai_api_messages(self):
        """Convert the conversation to OpenAI chat completion format."""
        ret = [{"role": "system", "content": self.system}]

        for i, (_, msg) in enumerate(self.messages[self.offset:]):
            if i % 2 == 0:
                ret.append({"role": "user", "content": msg})
            else:
                if msg is not None:
                    ret.append({"role": "assistant", "content": msg})
        return ret

    def copy(self):
        return Conversation(
            name=self.name,
            system=self.system,
            roles=self.roles,
            messages=[[x, y] for x, y in self.messages],
            offset=self.offset,
            sep_style=self.sep_style,
            sep=self.sep,
            sep2=self.sep2,
            stop_str=self.stop_str,
            stop_token_ids=self.stop_token_ids,
            conv_id=self.conv_id,
            model_name=self.model_name,
        )

    def dict(self):
        return {
            "name": self.name,
            "system": self.system,
            "roles": self.roles,
            "messages": self.messages,
            "offset": self.offset,
            "conv_id": self.conv_id,
            "model_name": self.model_name,
        }


# A global registry for all conversation templates
conv_templates: Dict[str, Conversation] = {}


def register_conv_template(template: Conversation, override: bool = False):
    """Register a new conversation template."""
    if not override:
        assert template.name not in conv_templates, f"{template.name} has been registered."
    conv_templates[template.name] = template


def get_conv_template(name: str) -> Conversation:
    """Get a conversation template."""
    return conv_templates[name].copy()


# A template with one conversation example
register_conv_template(
    Conversation(
        name="one_shot",
        system="A chat between a curious human and an artificial intelligence assistant. "
               "The assistant gives helpful, detailed, and polite answers to the human's questions.",
        roles=("Human", "Assistant"),
        messages=(
            (
                "Human",
                "What are the key differences between renewable and non-renewable energy sources?",
            ),
            (
                "Assistant",
                "Renewable energy sources are those that can be replenished naturally in a relatively "
                "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
                "Non-renewable energy sources, on the other hand, are finite and will eventually be "
                "depleted, such as coal, oil, and natural gas. Here are some key differences between "
                "renewable and non-renewable energy sources:\n"
                "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
                "energy sources are finite and will eventually run out.\n"
                "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
                "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
                "and other negative effects.\n"
                "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
                "have lower operational costs than non-renewable sources.\n"
                "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
                "locations than non-renewable sources.\n"
                "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
                "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
                "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
                "non-renewable sources are not, and their depletion can lead to economic and social instability.",
            ),
        ),
        offset=2,
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n### ",
        stop_str="###",
    )
)

# Vicuna v1.1 template
register_conv_template(
    Conversation(
        name="vicuna_v1.1",
        system="A chat between a curious user and an artificial intelligence assistant. "
               "The assistant gives helpful, detailed, and polite answers to the user's questions.",
        roles=("USER", "ASSISTANT"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep=" ",
        sep2="</s>",
    )
)

# Koala default template
register_conv_template(
    Conversation(
        name="koala_v1",
        system="BEGINNING OF CONVERSATION:",
        roles=("USER", "GPT"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.ADD_COLON_TWO,
        sep=" ",
        sep2="</s>",
    )
)

# Dolly V2 default template
register_conv_template(
    Conversation(
        name="dolly_v2",
        system="Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n",
        roles=("### Instruction", "### Response"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.DOLLY,
        sep="\n\n",
        sep2="### End",
    )
)

# OpenAssistant Pythia default template
register_conv_template(
    Conversation(
        name="oasst_pythia",
        system="",
        roles=("<|prompter|>", "<|assistant|>"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="<|endoftext|>",
    )
)

# StableLM Alpha default template
register_conv_template(
    Conversation(
        name="stablelm",
        system="""<|SYSTEM|># StableLM Tuned (Alpha version)
- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
- StableLM will refuse to participate in anything that could harm a human.
""",
        roles=("<|USER|>", "<|ASSISTANT|>"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.NO_COLON_SINGLE,
        sep="",
        stop_token_ids=[50278, 50279, 50277, 1, 0],
    )
)

# Baize default template
register_conv_template(
    Conversation(
        name="baize",
        system="The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.",
        roles=("[|Human|]", "[|AI|]"),
        messages=(
            ("[|Human|]", "Hello!"),
            ("[|AI|]", "Hi!"),
        ),
        offset=2,
        sep_style=SeparatorStyle.BAIZE,
        sep="[|Human|]",
        stop_str="[|Human|]",
    )
)

# RWKV-4-Raven default template
register_conv_template(
    Conversation(
        name="rwkv",
        system="The following is a coherent verbose detailed conversation between Bob and Alice.\n\n",
        roles=("Bob", "Alice"),
        messages=(
            ("Bob", "Hi"),
            (
                "Alice",
                "Hi. I am your assistant and I will answer all questions. Please feel free to ask any question and I will always answer it.",
            ),
        ),
        offset=2,
        sep_style=SeparatorStyle.RWKV,
        sep="",
        stop_str="\n\n",
    )
)

# Buddy default template
register_conv_template(
    Conversation(
        name="openbuddy",
        system="""Consider a conversation between User (a human) and Assistant (named Buddy).
Buddy is an INTP-T, a friendly, intelligent and multilingual AI assistant, by OpenBuddy team. GitHub: https://github.com/OpenBuddy/OpenBuddy
Buddy cannot access the Internet.
Buddy can fluently speak the user's language (e.g. English, Chinese).
Buddy can generate poems, stories, code, essays, songs, parodies, and more.
Buddy possesses vast knowledge about the world, history, and culture.
Buddy's responses are always safe, creative, high-quality, human-like, and interesting.
Buddy strictly refuses to discuss political, NSFW, or other unsafe topics.

User: Hi.
Assistant: Hi, I'm Buddy, your AI assistant. How can I help you today?""",
        roles=("User", "Assistant"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n",
    )
)

# Phoenix default template
register_conv_template(
    Conversation(
        name="phoenix",
        system="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
        roles=("Human", "Assistant"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.PHOENIX,
        sep="</s>",
    )
)

# ChatGPT default template
register_conv_template(
    Conversation(
        name="chatgpt",
        system="You are a helpful assistant.",
        roles=("user", "assistant"),
        messages=(),
        offset=0,
        sep_style=None,
        sep=None,
    )
)

# Claude default template
register_conv_template(
    Conversation(
        name="claude",
        system="",
        roles=("Human", "Assistant"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
        sep="\n\n",
    )
)

# MPT default template
register_conv_template(
    Conversation(
        name="mpt",
        system="""<|im_start|>system
- You are a helpful assistant chatbot trained by MosaicML.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.
""",
        roles=("<|im_start|>user", "<|im_start|>assistant"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.NEW_LINE,
        sep="<|im_end|>",
        stop_token_ids=[50278, 0],
    )
)

# Bard default template
# Reference: https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L150
#            https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L40
register_conv_template(
    Conversation(
        name="bard",
        system="",
        roles=("0", "1"),
        messages=(),
        offset=0,
        sep_style=None,
        sep=None,
    )
)

# BiLLa default template
register_conv_template(
    Conversation(
        name="billa",
        system="",
        roles=("Human", "Assistant"),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.BILLA,
        sep="\n",
        stop_str="Human:",
    )
)

# custom otter template
register_conv_template(
    Conversation(
        name='otter',
        system='',
        roles=('User:', 'GPT:<answer>'),
        messages=(),
        offset=0,
        sep_style=SeparatorStyle.ADD_SPACE_TWO,
        sep=' ',
        sep2='<|endofchunk|>',
    )
)

if __name__ == "__main__":
    conv = get_conv_template("vicuna_v1.1")
    conv.append_message(conv.roles[0], "Hello!")
    conv.append_message(conv.roles[1], "Hi!")
    conv.append_message(conv.roles[0], "How are you?")
    conv.append_message(conv.roles[1], None)
    print(conv.get_prompt())